A survey on text generation using generative adversarial networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.patcog.2021.108098 http://hdl.handle.net/11449/229013 |
Resumo: | This work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks. The usage of adversarial learning for text generation is promising as it provides alternatives to generate the so-called “natural” language. Nevertheless, adversarial text generation is not a simple task as its foremost architecture, the Generative Adversarial Networks, were designed to cope with continuous information (image) instead of discrete data (text). Thus, most works are based on three possible options, i.e., Gumbel-Softmax differentiation, Reinforcement Learning, and modified training objectives. All alternatives are reviewed in this survey as they present the most recent approaches for generating text using adversarial-based techniques. The selected works were taken from renowned databases, such as Science Direct, IEEEXplore, Springer, Association for Computing Machinery, and arXiv, whereas each selected work has been critically analyzed and assessed to present its objective, methodology, and experimental results. |
id |
UNSP_1c250a5d212ce3e6a390c06b80746cf4 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/229013 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A survey on text generation using generative adversarial networksGenerative adversarial NetworksLanguage modelingMachine learningNatural language processingText generationThis work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks. The usage of adversarial learning for text generation is promising as it provides alternatives to generate the so-called “natural” language. Nevertheless, adversarial text generation is not a simple task as its foremost architecture, the Generative Adversarial Networks, were designed to cope with continuous information (image) instead of discrete data (text). Thus, most works are based on three possible options, i.e., Gumbel-Softmax differentiation, Reinforcement Learning, and modified training objectives. All alternatives are reviewed in this survey as they present the most recent approaches for generating text using adversarial-based techniques. The selected works were taken from renowned databases, such as Science Direct, IEEEXplore, Springer, Association for Computing Machinery, and arXiv, whereas each selected work has been critically analyzed and assessed to present its objective, methodology, and experimental results.Department of Computing São Paulo State University BauruDepartment of Computing São Paulo State University BauruUniversidade Estadual Paulista (UNESP)de Rosa, Gustavo H. [UNESP]Papa, João P. [UNESP]2022-04-29T08:29:58Z2022-04-29T08:29:58Z2021-11-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1016/j.patcog.2021.108098Pattern Recognition, v. 119.0031-3203http://hdl.handle.net/11449/22901310.1016/j.patcog.2021.1080982-s2.0-85108354229Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengPattern Recognitioninfo:eu-repo/semantics/openAccess2024-04-23T16:10:46Zoai:repositorio.unesp.br:11449/229013Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:56:32.250197Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A survey on text generation using generative adversarial networks |
title |
A survey on text generation using generative adversarial networks |
spellingShingle |
A survey on text generation using generative adversarial networks de Rosa, Gustavo H. [UNESP] Generative adversarial Networks Language modeling Machine learning Natural language processing Text generation |
title_short |
A survey on text generation using generative adversarial networks |
title_full |
A survey on text generation using generative adversarial networks |
title_fullStr |
A survey on text generation using generative adversarial networks |
title_full_unstemmed |
A survey on text generation using generative adversarial networks |
title_sort |
A survey on text generation using generative adversarial networks |
author |
de Rosa, Gustavo H. [UNESP] |
author_facet |
de Rosa, Gustavo H. [UNESP] Papa, João P. [UNESP] |
author_role |
author |
author2 |
Papa, João P. [UNESP] |
author2_role |
author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
de Rosa, Gustavo H. [UNESP] Papa, João P. [UNESP] |
dc.subject.por.fl_str_mv |
Generative adversarial Networks Language modeling Machine learning Natural language processing Text generation |
topic |
Generative adversarial Networks Language modeling Machine learning Natural language processing Text generation |
description |
This work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks. The usage of adversarial learning for text generation is promising as it provides alternatives to generate the so-called “natural” language. Nevertheless, adversarial text generation is not a simple task as its foremost architecture, the Generative Adversarial Networks, were designed to cope with continuous information (image) instead of discrete data (text). Thus, most works are based on three possible options, i.e., Gumbel-Softmax differentiation, Reinforcement Learning, and modified training objectives. All alternatives are reviewed in this survey as they present the most recent approaches for generating text using adversarial-based techniques. The selected works were taken from renowned databases, such as Science Direct, IEEEXplore, Springer, Association for Computing Machinery, and arXiv, whereas each selected work has been critically analyzed and assessed to present its objective, methodology, and experimental results. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-11-01 2022-04-29T08:29:58Z 2022-04-29T08:29:58Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1016/j.patcog.2021.108098 Pattern Recognition, v. 119. 0031-3203 http://hdl.handle.net/11449/229013 10.1016/j.patcog.2021.108098 2-s2.0-85108354229 |
url |
http://dx.doi.org/10.1016/j.patcog.2021.108098 http://hdl.handle.net/11449/229013 |
identifier_str_mv |
Pattern Recognition, v. 119. 0031-3203 10.1016/j.patcog.2021.108098 2-s2.0-85108354229 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Pattern Recognition |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128724847034368 |